Agentopic: A Generative AI Agent Workflow for Explainable Topic Modeling
For practitioners in high-stakes domains like finance and healthcare, Agentopic offers an interpretable alternative to black-box topic models without sacrificing accuracy.
Agentopic introduces an agent-based workflow for explainable topic modeling using LLMs, achieving an F1-score of 0.95 on the BBC dataset, matching GPT-4.1 and close to BERTopic's 0.98, while providing transparent reasoning for topic assignments.
Agentopic is a novel agent-based workflow for explainable topic modeling that leverages the reasoning capabilities of Large Language Models (LLMs). Existing topic modeling approaches such as Latent Dirichlet Allocation (LDA) and BERTopic often lack transparency on how topics are assigned or grouped. Agentopic addresses this by using multiple agents that collaboratively perform topic identification, validation, hierarchical grouping, and natural language explanation. This design enables users to trace the reasoning behind topic assignments, enhancing interpretability without sacrificing accuracy. When seeded with topics from the British Broadcasting Corporation (BBC) dataset, Agentopic achieves an F1-score of 0.95, matching GPT-4.1, improving on LDA (0.93), and close to BERTopic (0.98). We used Agentopic to augment the BBC dataset with generated explanations to improve the dataset's richness and context. The unseeded Agentopic generated 2045 semantically coherent topics organized across six hierarchical levels, vastly enriching the original five-category structure. By embedding explainability throughout the workflow, Agentopic offers an interpretable alternative to black-box models, making it particularly valuable for crucial applications like finance and healthcare.